Self-Driving Car
Neural networks evolve to drive cars around randomly generated tracks using distance sensors.
Generation1
Best Fitness0
Cars Alive0
Distance0
About This Simulation
This simulation demonstrates the NEAT algorithm applied to evolving neural networks that can drive cars around randomly generated tracks. Each generation tests on a newly generated track to prevent overspecialization.
Technical Details
Neural Network Inputs: 5 distance sensors that detect track boundaries
Neural Network Outputs: Steering angle and acceleration
Fitness Function: Based on distance traveled and checkpoints passed
Population Size: 50 cars per generation